10 citations · 17 across the 9 of their papers we have counts for
11 papers
Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation
Zixu Wang, Xiaoran Zhao, Yahui Liu +8
Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challenging. Existing agentic approach…
Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
Zhizhao Liu, Zhiliang Tian, Xi Wang +4
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the same expl…
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations
Xinyue Fang, Zhiliang Tian, Zhen Huang +5
Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models'internal knowledge or have poor cross-domain generali…
Role-aware Heuristic Episodic Attention for Conversational LLMs
Wanyang Hong, Zhaoning Zhang, Yi Chen +5
Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three…
Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling
Xinyue Fang, Zhen Huang, Zhiliang Tian +6
LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that ar…
LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions
Xiaoran Zhao, Tianhao Wu, Yu Lai +5
Controllable text-to-image generation synthesizes visual text and objects in images with certain conditions, which are frequently applied to emoji and poster generation. Visual tex…
TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features
Hengyue Pan, Yixin Chen, Zhiliang Tian +3
Convolutional neural network (CNN) has achieved impressive success in computer vision during the past few decades. The image convolution operation helps CNNs to get good performanc…
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
Shilong Pan, Zhiliang Tian, Liang Ding +3
Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neur…
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery
Zimian Wei, Lujun Li, Peijie Dong +6
The substantial success of Vision Transformer (ViT) in computer vision tasks is largely attributed to the architecture design. This underscores the necessity of efficient architect…
TVT: Training-Free Vision Transformer Search on Tiny Datasets
Zimian Wei, Hengyue Pan, Lujun Li +4
Training-free Vision Transformer (ViT) architecture search is presented to search for a better ViT with zero-cost proxies. While ViTs achieve significant distillation gains from CN…
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence
Zhihua Wen, Zhiliang Tian, Wei Wu +4
Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on m…